Autonomous closed-loop adaptive therapy driven by blood tests and evolutionary models
Rather than giving the same dose until the cancer grows, measure tumour DNA in blood every few weeks and let a validated algorithm raise, lower, pause or switch drugs to keep the cancer suppressed for longer.
Adaptive therapy trials in prostate cancer (PSA-guided abiraterone cycling at Moffitt) suggest that modulating dose to maintain competition between sensitive and resistant cells can extend control. Circulating tumour DNA now allows frequent, clone-resolved monitoring across cancers. The proposal is a closed-loop system: serial ctDNA and imaging feed an evolutionary model that recommends dose and drug changes under pre-specified rules, with clinician oversight, tested first in oncogene-driven lung cancer and hormone-sensitive prostate cancer.
- Acquired resistance to every therapy · Nearly every targeted therapy stops working within months to a few years as the tumour adapts.
- Wrong doses · Most drug doses were chosen as the highest a person can tolerate, which is often more than they need.
- AI that is built but not validated or deployed · Thousands of cancer AI models are published; a handful are in clinical use, and fewer have shown they help patients.
Pages like this
not linked directly; found by shared links- IdeactDNA-guided dose holidays for lung cancer targeted therapy
Shares Osimertinib, Circulating tumour DNA (ctDNA), Wrong doses, Acquired resistance to every therapy.
- IdeaEvolution-guided 'adaptive therapy' dosing tested in randomised phase 2 trials
Shares Moffitt Cancer Center, Drug resistance (primary and acquired), Wrong doses, Acquired resistance to every therapy.
- IdeaTest intermittent dosing of targeted drugs to delay resistance, with honest priors
Shares Drug resistance (primary and acquired), Circulating tumour DNA (ctDNA), Wrong doses, Acquired resistance to every therapy.
- IdeaForecast the next resistance mutation like the weather
Shares Drug resistance (primary and acquired), Osimertinib, AI that is built but not validated or deployed, Acquired resistance to every therapy.
- IdeaPause a failed drug so the tumour becomes sensitive to it again
Shares Drug resistance (primary and acquired), Osimertinib, Acquired resistance to every therapy, Liquid biopsy (ctDNA).
- IdeaFund a biopsy at progression, every time, as standard care
Shares Drug resistance (primary and acquired), Circulating tumour DNA (ctDNA), Acquired resistance to every therapy, Liquid biopsy (ctDNA).
- IdeaSMART designs to test treatment strategies, not just single drugs
Shares Drug resistance (primary and acquired), Circulating tumour DNA (ctDNA), Acquired resistance to every therapy, Prostate cancer.
- PersonRobert A. Gatenby
Shares Moffitt Cancer Center, Drug resistance (primary and acquired), Prostate cancer.